Upload app.py

app.py

@@ -0,0 +1,105 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import re
+
+# --- 1. CONFIGURATION ---
+# Replace this with your actual model path on Hugging Face
+MODEL_NAME = "YOUR_USERNAME/AraBERT-Arabic-Sentiment"
+
+# Map your labels matching your training (0: Negative, 1: Neutral, 2: Positive)
+LABELS = {
+    0: "Negative 😞", 
+    1: "Neutral 😐", 
+    2: "Positive 😃"
+}
+
+# --- 2. LOAD MODEL & TOKENIZER ---
+print(f"Loading model: {MODEL_NAME}...")
+try:
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+    print("Model loaded successfully!")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    raise e
+
+# --- 3. PREPROCESSING FUNCTION ---
+# We replicate the basic cleaning you did in training to ensure accuracy
+def clean_text(text):
+    if not isinstance(text, str):
+        return ""
+    
+    # Remove HTML tags and URLs
+    text = re.sub(r'http\S+', '', text)
+    text = re.sub(r'<.*?>', '', text)
+    
+    # Keep only Arabic letters and spaces (Basic noise removal)
+    # This regex keeps Arabic chars, spaces, and common punctuation
+    text = re.sub(r'[^\w\s\u0600-\u06FF]', ' ', text)
+    
+    # Normalize Alef (أ, إ, آ -> ا)
+    text = re.sub(r'[أإآ]', 'ا', text)
+    # Normalize Teh Marbuta (ة -> ه)
+    text = re.sub(r'ة', 'ه', text)
+    
+    return text.strip()
+
+# --- 4. PREDICTION FUNCTION ---
+def predict(text):
+    # 1. Clean
+    cleaned_text = clean_text(text)
+    
+    # 2. Tokenize
+    inputs = tokenizer(
+        cleaned_text, 
+        return_tensors="pt", 
+        truncation=True, 
+        padding=True, 
+        max_length=128
+    )
+    
+    # 3. Inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+        
+    # 4. Get Probabilities (Softmax)
+    probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+    
+    # 5. Format Output for Gradio (Label -> Probability)
+    # Gradio expects a dictionary: {"Positive": 0.9, "Negative": 0.1}
+    results = {}
+    for idx, score in enumerate(probs[0]):
+        label_text = LABELS[idx]
+        results[label_text] = float(score)
+        
+    return results
+
+# --- 5. BUILD INTERFACE ---
+# We use a clean, professional theme
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(
+        label="أدخل تعليق الطالب (Enter Student Feedback)", 
+        placeholder="اكتب هنا... (مثال: الشرح كان ممتاز واستفدت جدا)",
+        lines=3,
+        text_align="right"  # RTL support for Arabic
+    ),
+    outputs=gr.Label(label="Sentiment Analysis Result", num_top_classes=3),
+    title="📊 Arabic Course Feedback Analyzer",
+    description="""
+    This is an AI-powered tool to analyze student feedback using **Deep Learning (AraBERT)**.
+    It detects whether the sentiment is **Positive**, **Negative**, or **Neutral**.
+    """,
+    examples=[
+        ["الكورس ممتاز والشرح كان رائع جدا"],
+        ["بصراحة ضيعت وقتي، المحتوى ضعيف"],
+        ["الكورس عادي يعني لا وحش ولا حلو"],
+        ["الشرح كويس بس الصوت كان واطي في بعض الفيديوهات"]
+    ],
+    theme=gr.themes.Soft()
+)
+
+# Launch
+if __name__ == "__main__":
+    demo.launch()